[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M753W2F7FSPV5V445N7T3ZBV":3,"skill-same:01M753W2F7FSPV5V445N7T3ZBV":55},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":29,"commitSha":30,"skillDirectory":5,"forksCount":14,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":33,"ownerDescription":6,"updatedAt":34,"install":35,"resources":48},"01M753W2F7FSPV5V445N7T3ZBV","mistral-reference-architecture",null,"Implement Mistral AI reference architecture with best-practice project layout.\nUse when designing new Mistral AI integrations, reviewing project structure,\nor establishing architecture standards for Mistral AI applications.\nTrigger with phrases like \"mistral architecture\", \"mistral best practices\",\n\"mistral project structure\", \"how to organize mistral\", \"mistral layout\".","SamuelChien\u002Fmega-skills-collection","SamuelChien","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F4652114?v=4","01M74KK34WVHA0P5ZYSJRDDFMG","Samuel Chien","01M74KK35FQN1N9VZ9EPTH3P2S",0,"MIT","https:\u002F\u002Fgithub.com\u002FSamuelChien\u002Fmega-skills-collection\u002Fblob\u002Fmain\u002Fmistral-reference-architecture\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: mistral-reference-architecture\ndescription: |\n  Implement Mistral AI reference architecture with best-practice project layout.\n  Use when designing new Mistral AI integrations, reviewing project structure,\n  or establishing architecture standards for Mistral AI applications.\n  Trigger with phrases like \"mistral architecture\", \"mistral best practices\",\n  \"mistral project structure\", \"how to organize mistral\", \"mistral layout\".\nallowed-tools: Read, Grep\nversion: 1.0.0\nlicense: MIT\nauthor: Jeremy Longshore \u003Cjeremy@intentsolutions.io>\ncompatible-with: claude-code, codex, openclaw\n---\n# Mistral AI Reference Architecture\n\n## Table of Contents\n- [Overview](#overview)\n- [Prerequisites](#prerequisites)\n- [Instructions](#instructions)\n- [Output](#output)\n- [Error Handling](#error-handling)\n- [Examples](#examples)\n- [Resources](#resources)\n\n## Overview\nProduction-ready architecture patterns for Mistral AI integrations. Covers layered project structure, client singleton, configuration management, error handling, service layer with caching, health checks, and prompt templates.\n\n## Prerequisites\n- Understanding of layered architecture\n- Mistral AI SDK knowledge\n- TypeScript project setup\n- Testing framework configured\n\n## Layer Architecture\n\n```\nAPI Layer (Routes, Controllers, Middleware)\n    ↓\nService Layer (Business Logic, Orchestration)\n    ↓\nMistral Layer (Client, Prompts, Error Handling)\n    ↓\nInfrastructure Layer (Cache, Queue, Monitoring)\n```\n\n## Instructions\n\n### Step 1: Create Directory Structure\nOrganize into `src\u002Fmistral\u002F` (client, config, types, errors, prompts, handlers), `src\u002Fservices\u002Fai\u002F` (chat, rag, cache), `src\u002Fapi\u002F` (routes, streaming), `tests\u002F` (unit, integration), and `config\u002F` (per-environment JSON).\n\n### Step 2: Implement Client Singleton\nCreate `getMistralClient()` factory that lazily initializes a single `Mistral` instance with config from environment. Include `resetMistralClient()` for testing.\n\n### Step 3: Configure with Zod Validation\nDefine config schema with `z.object()` for apiKey, model (default `mistral-small-latest`), timeout (30s), maxRetries (3), and cache settings. Parse from environment variables.\n\n### Step 4: Build Error Handling Layer\nCreate `MistralServiceError` class with code, status, retryable flag. Wrap raw errors: 429 = RATE_LIMIT (retryable), 401 = AUTH_ERROR, 500+ = SERVICE_ERROR (retryable).\n\n### Step 5: Implement Service Layer\nBuild `ChatService` with `complete()` and `stream()` methods. Add cache check for deterministic requests (temperature=0). Wrap all calls with retry and error handling.\n\n### Step 6: Add Health Check\nImplement `checkMistralHealth()` that calls `client.models.list()` and returns status (healthy\u002Fdegraded\u002Funhealthy) with latency measurement.\n\n### Step 7: Create Prompt Templates\nDefine reusable `PromptTemplate` interface with system prompt and user template function. Include templates for summarize, classify, and codeReview.\n\n## Output\n- Structured project layout with clear layer separation\n- Client singleton wrapper with retry logic\n- Zod-validated configuration management\n- Custom error classes with retryable detection\n- Service layer with caching and streaming\n- Health check endpoint\n- Reusable prompt templates\n\n## Error Handling\n| Issue | Cause | Resolution |\n|-------|-------|------------|\n| Rate limit (429) | Too many requests | Retry with backoff, marked retryable |\n| Auth error (401) | Invalid API key | Check credentials, not retryable |\n| Server error (5xx) | Mistral service issue | Retry with backoff, marked retryable |\n| Config validation | Missing\u002Finvalid env vars | Check Zod schema errors |\n\n## Examples\n\n### Client Usage\n```typescript\nconst client = getMistralClient();\nconst response = await client.chat.complete({\n  model: 'mistral-small-latest',\n  messages: [{ role: 'user', content: 'Hello' }],\n});\n```\n\nSee [detailed implementation](${CLAUDE_SKILL_DIR}\u002Freferences\u002Fimplementation.md) for advanced patterns.\n\n## Resources\n- [Mistral AI API Reference](https:\u002F\u002Fdocs.mistral.ai\u002Fapi\u002F)\n- [Clean Architecture](https:\u002F\u002Fblog.cleancoder.com\u002Funcle-bob\u002F2012\u002F08\u002F13\u002Fthe-clean-architecture.html)","# Mistral AI Reference Architecture\n\n## Table of Contents\n- [Overview](#overview)\n- [Prerequisites](#prerequisites)\n- [Instructions](#instructions)\n- [Output](#output)\n- [Error Handling](#error-handling)\n- [Examples](#examples)\n- [Resources](#resources)\n\n## Overview\nProduction-ready architecture patterns for Mistral AI integrations. Covers layered project structure, client singleton, configuration management, error handling, service layer with caching, health checks, and prompt templates.\n\n## Prerequisites\n- Understanding of layered architecture\n- Mistral AI SDK knowledge\n- TypeScript project setup\n- Testing framework configured\n\n## Layer Architecture\n\n```\nAPI Layer (Routes, Controllers, Middleware)\n    ↓\nService Layer (Business Logic, Orchestration)\n    ↓\nMistral Layer (Client, Prompts, Error Handling)\n    ↓\nInfrastructure Layer (Cache, Queue, Monitoring)\n```\n\n## Instructions\n\n### Step 1: Create Directory Structure\nOrganize into `src\u002Fmistral\u002F` (client, config, types, errors, prompts, handlers), `src\u002Fservices\u002Fai\u002F` (chat, rag, cache), `src\u002Fapi\u002F` (routes, streaming), `tests\u002F` (unit, integration), and `config\u002F` (per-environment JSON).\n\n### Step 2: Implement Client Singleton\nCreate `getMistralClient()` factory that lazily initializes a single `Mistral` instance with config from environment. Include `resetMistralClient()` for testing.\n\n### Step 3: Configure with Zod Validation\nDefine config schema with `z.object()` for apiKey, model (default `mistral-small-latest`), timeout (30s), maxRetries (3), and cache settings. Parse from environment variables.\n\n### Step 4: Build Error Handling Layer\nCreate `MistralServiceError` class with code, status, retryable flag. Wrap raw errors: 429 = RATE_LIMIT (retryable), 401 = AUTH_ERROR, 500+ = SERVICE_ERROR (retryable).\n\n### Step 5: Implement Service Layer\nBuild `ChatService` with `complete()` and `stream()` methods. Add cache check for deterministic requests (temperature=0). Wrap all calls with retry and error handling.\n\n### Step 6: Add Health Check\nImplement `checkMistralHealth()` that calls `client.models.list()` and returns status (healthy\u002Fdegraded\u002Funhealthy) with latency measurement.\n\n### Step 7: Create Prompt Templates\nDefine reusable `PromptTemplate` interface with system prompt and user template function. Include templates for summarize, classify, and codeReview.\n\n## Output\n- Structured project layout with clear layer separation\n- Client singleton wrapper with retry logic\n- Zod-validated configuration management\n- Custom error classes with retryable detection\n- Service layer with caching and streaming\n- Health check endpoint\n- Reusable prompt templates\n\n## Error Handling\n| Issue | Cause | Resolution |\n|-------|-------|------------|\n| Rate limit (429) | Too many requests | Retry with backoff, marked retryable |\n| Auth error (401) | Invalid API key | Check credentials, not retryable |\n| Server error (5xx) | Mistral service issue | Retry with backoff, marked retryable |\n| Config validation | Missing\u002Finvalid env vars | Check Zod schema errors |\n\n## Examples\n\n### Client Usage\n```typescript\nconst client = getMistralClient();\nconst response = await client.chat.complete({\n  model: 'mistral-small-latest',\n  messages: [{ role: 'user', content: 'Hello' }],\n});\n```\n\nSee [detailed implementation](${CLAUDE_SKILL_DIR}\u002Freferences\u002Fimplementation.md) for advanced patterns.\n\n## Resources\n- [Mistral AI API Reference](https:\u002F\u002Fdocs.mistral.ai\u002Fapi\u002F)\n- [Clean Architecture](https:\u002F\u002Fblog.cleancoder.com\u002Funcle-bob\u002F2012\u002F08\u002F13\u002Fthe-clean-architecture.html)",{"name":5,"author":24,"license":15,"version":25,"description":26,"allowed-tools":27,"compatible-with":28},"Jeremy Longshore \u003Cjeremy@intentsolutions.io>","1.0.0","Implement Mistral AI reference architecture with best-practice project layout.\nUse when designing new Mistral AI integrations, reviewing project structure,\nor establishing architecture standards for Mistral AI applications.\nTrigger with phrases like \"mistral architecture\", \"mistral best practices\",\n\"mistral project structure\", \"how to organize mistral\", \"mistral layout\".\n","Read, Grep","claude-code, codex, openclaw","main","c2b1fdccc779e99ac814e55fb69ca8d71215dd0f","https:\u002F\u002Fgithub.com\u002FSamuelChien\u002Fmega-skills-collection","https:\u002F\u002Fgithub.com\u002FSamuelChien","http:\u002F\u002Fsamuelchien.com\u002F","2026-05-26 08:27:14",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add SamuelChien\u002Fmega-skills-collection --skill mistral-reference-architecture",{"tool":41,"command":42},"bunx","bunx skills add SamuelChien\u002Fmega-skills-collection --skill mistral-reference-architecture",{"tool":44,"command":45},"pnpm","pnpm dlx skills add SamuelChien\u002Fmega-skills-collection --skill mistral-reference-architecture","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSamuelChien\u002Fmega-skills-collection\u002Fblob\u002Fmain\u002Fmistral-reference-architecture\u002FSKILL.md",true,[49],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002Fimplementation.md","REFERENCE","参考文档",2908,"https:\u002F\u002Fgithub.com\u002FSamuelChien\u002Fmega-skills-collection\u002Fblob\u002Fmain\u002Fmistral-reference-architecture\u002Freferences\u002Fimplementation.md",[56,63,70,77,84,92],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M76R4WZQZAXGGXMQCA0FZ716","zustand-store-ts","Create Zustand stores with TypeScript, subscribeWithSelector middleware, and proper state\u002Faction separation. Use when building React state management, creating global stores, or implementing reactive state patterns with Zustand.","https:\u002F\u002Fgithub.com\u002FSamuelChien\u002Fmega-skills-collection\u002Fblob\u002Fmain\u002Fzustand-store-ts\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M76R4T9KENDH7FENGZQHBW4G","zustand-store-creator","Zustand Store Creator - Auto-activating skill for Frontend Development.\nTriggers on: zustand store creator, zustand store creator\nPart of the Frontend Development skill category.","https:\u002F\u002Fgithub.com\u002FSamuelChien\u002Fmega-skills-collection\u002Fblob\u002Fmain\u002Fzustand-store-creator\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M76R3YWN84B7SANJ52X799ZE","zero-trust-config-helper","Zero Trust Config Helper - Auto-activating skill for Security Advanced.\nTriggers on: zero trust config helper, zero trust config helper\nPart of the Security Advanced skill category.","https:\u002F\u002Fgithub.com\u002FSamuelChien\u002Fmega-skills-collection\u002Fblob\u002Fmain\u002Fzero-trust-config-helper\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M76R3HNSV2AEYSKHM915GJ58","zapier-integration-helper","Zapier Integration Helper - Auto-activating skill for Business Automation.\nTriggers on: zapier integration helper, zapier integration helper\nPart of the Business Automation skill category.","https:\u002F\u002Fgithub.com\u002FSamuelChien\u002Fmega-skills-collection\u002Fblob\u002Fmain\u002Fzapier-integration-helper\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":88,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":19},"01M76R3DJSKAT4FA7DV4BF3GCE","zai-cli","Execute z.AI CLI providing vision, search, reader, and GitHub exploration via CLI and MCP.\nUse when user needs image\u002Fvideo analysis, OCR, UI-to-code conversion, error diagnosis,\nreal-time web search, web page to markdown extraction, or GitHub code exploration.\nTrigger with phrases like \"analyze this image\", \"search the web for\", \"read this page\",\n\"explore this repo\", or \"use zai\". Requires Z_AI_API_KEY.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FSamuelChien\u002Fmega-skills-collection\u002Fblob\u002Fmain\u002Fzai-cli\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":19},"01M76R2KAM699XE9AJVAWE4H2E","yt-research","Research competitor YouTube channels, niches, and trending topics for your content strategy.\nUse this skill whenever the user says \"research channels\", \"analyze competitors\", \"find trending topics\",\n\"niche analysis\", \"competitive research\", \"what are other creators doing\", \"scrape YouTube channels\",\nor wants to understand the competitive landscape for a specific tool or topic area. Use when working with yt research. Trigger with 'yt', 'research'.","https:\u002F\u002Fgithub.com\u002FSamuelChien\u002Fmega-skills-collection\u002Fblob\u002Fmain\u002Fyt-research\u002FSKILL.md",[],[]]